Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to serious issues or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onas
    -0.17
    ukt
    -0.16
    jar
    -0.16
    ensex
    -0.15
    ersion
    -0.14
    Jar
    -0.14
    swire
    -0.14
    cales
    -0.14
    á»iji
    -0.14
     kamp
    -0.14
    POSITIVE LOGITS
     Chun
    0.16
     serious
    0.15
    deep
    0.15
    -league
    0.14
    -minded
    0.14
    erb
    0.14
     enough
    0.14
     Sunder
    0.14
     Serious
    0.14
     har
    0.14
    Act Density 0.013%

    No Known Activations